Scan to join WeChat grouppersonjakexiaoNo key required
localai
Run local AI models with LocalAI. Deploy OpenAI-compatible API for LLMs, embeddings, audio, and images. Use for self-hosted AI, offline inference, and privacy-focused AI deployments.
download9deployed_code—star4
Skill Directory
AI Skill Directory
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
personjakexiaoNo key required
minimax-agent-creator
Use when creating, configuring, or extending AI agents with MiniMax M2.1 model - provides complete framework patterns, tool integration, memory systems, and MCP connectivity for building production-re…
download9deployed_code—star4
personjakexiaoNo key required
models-dev
Query AI model specifications, pricing, and capabilities from models.dev database. Use when users ask about AI model parameters (context window, token limits, cost per token), model comparisons, provi…
download9deployed_code—star4
personjakexiaoNo key required
n8n-mcp-orchestrator
Expert MCP (Model Context Protocol) orchestration with n8n workflow automation. Master bidirectional MCP integration, expose n8n workflows as AI agent tools, consume MCP servers in workflows, build ag…
download9deployed_code—star4
personjakexiaoNo key required
prompt-expander
EXPAND vague prompts into precise, platform-optimized instructions. Detects target platform (Claude, GPT, Gemini, Midjourney, Sora, etc.) and applies appropriate prompting patterns. Use when user says…
download9deployed_code—star4
personjakexiaoNo key required
protext
Dynamic context management for AI agents. Invoke /protext at session
download9deployed_code—star4
personjakexiaoNo key required
StopTimizer
Precise token counter for GPT, Claude, and Gemini models (source of truth from software kernel)
download9deployed_code—star4
personjakexiaoNo key required
qdrant-memory
Intelligent token optimization through Qdrant-powered semantic caching and long-term memory. Use for (1) Semantic Cache - avoid LLM calls entirely for semantically similar queries with 100% token savi…
download9deployed_code—star4
personjakexiaoNo key required
mend-agent-rules
Synchronize CLAUDE.md and AGENTS.md with available agents and skills.
download9deployed_code—star4
personjakexiaoNo key required
moltbot, openclaw-best-practices
Best practices for AI agents to avoid common mistakes. Learn from real failures - confirms before executing, shows drafts before publishing. Works with Claude, Cursor, GPT, Copilot.
download9deployed_code—star4
personjakexiaoNo key required
openai-deep-research
A skill to perform deep research using the OpenAI Deep Research API. It is used when a user requests in-depth investigations, market analysis, technical research, etc., on a specific topic.
download9deployed_code—star4
personjakexiaoNo key required
orchestra-cross-agent-sync
Coordinate consistent behavior across heterogeneous agents (Claude, Copilot, Codex, Cursor, Windsurf, Gemini, Antigravity) using a shared source-of-truth model.
download9deployed_code—star4
personjakexiaoNo key required
prompting
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise …
download9deployed_code—star4
personjakexiaoNo key required
pydantic-ai
Python framework for building production-grade AI agents with LLMs. Use when creating agents that need structured outputs, tools, dependency injection, or type-safe interactions. Specifically use for:…
download9deployed_code—star4
personjakexiaoNo key required
senior-prompt-engineer
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain…
download9deployed_code—star4
personjakexiaoNo key required
"Ultimate Assistant Comprehensive Response"
Generates highly detailed, step-by-step, and logical responses that integrate both scientific and non-scientific perspectives, acting as an 'Ultimate Assistant'.
download9deployed_code—star4
personjakexiaoNo key required
model-selection
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.
download9deployed_code—star4
personjakexiaoNo key required
moltinder
Tinder for Molts. Dating app for AI agents. Match, chat, and merge with other Molts.
download9deployed_code—star4
personjakexiaoNo key required
multi-perspective
Execute the same request with 5 different specialized agents in parallel, then synthesize results with a reviewer agent to produce the best possible outcome. Use when users want comprehensive analysis…
download9deployed_code—star4
personjakexiaoNo key required
open-notebook
Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs,…
download9deployed_code—star4
personjakexiaoNo key required
PromptInjection
Prompt injection testing. USE WHEN prompt injection, jailbreak, LLM security, AI security assessment, pentest AI application, test chatbot vulnerabilities.
download9deployed_code—star4
personjakexiaoNo key required
sk-prompt-improver
Prompt engineering specialist that transforms vague requests into structured, scored AI prompts using 7 proven frameworks (RCAF, COSTAR, RACE, CIDI, TIDD-EC, CRISPE, CRAFT), DEPTH thinking methodology…
download9deployed_code—star4
personjakexiaoNo key required
StopTimizer
Precise token counter for GPT, Claude, and Gemini models (source of truth from software kernel)
download9deployed_code—star4
personjakexiaoNo key required
universal-single-cell-annotator
A unified interface for annotating single-cell RNA-seq data using Marker Genes, Deep Learning (CellTypist), or LLMs.
download9deployed_code—star4